Bachelor/Master Theses and Master Project Topics
This pages lists the open BSc. and MSc. thesis descriptions, as well as the master projects opportunities currently available in the DDIS research group.
If you are interested in any of the listed projects, please do not hesitate to contact the person mentioned in the open topic description.
If there are currently no open topics but you are generally interested in our research (see https://www.ifi.uzh.ch/en/ddis/research.html), or if you would like to propose a thesis about your own idea, you can send us an email to ddis-theses@ifi.uzh.ch.
Master’s Thesis: Context-Aware Segmentation for Structured Understanding of Complex Documents
Many AI applications rely on underlying text documents. The various parts of the text documents often contain differing pieces of information relevant to processing. Identifying these pieces of information, however, is a non-trivial task. The goal of this thesis is, therefore, to segment heterogeneous documents—such as news articles or electronic health records—into semantically coherent and context-preserving chunks (or parts). Addressing limitations in sub-document level knowledge representation and retrieval, this work aims to develop a segmentation framework that detects context boundaries and constructs structured document representations.
In the first stage, this project explores the possibilities of leveraging semantic structures in news articles, using the fact that news providers adhere to specific structures. By aligning information across modalities, the model supports more effective downstream applications, including personalized recommendations, summarization, and information extraction.
The second stage of the project assesses the potential of domain transfer for the developed framework, specifically by applying semantic segmentation to electronic health record data with the aim of performing named entity recognition. As such, the thesis contributes to two ongoing research projects at DDIS: the Informfully and the RareSim projects.
Start Date: February 2026
Requirements: Strong Python coding skills, interest in knowledge graphs, and basic understanding of machine learning. Strongly recommended: the course Advanced Topics in Artificial Intelligence (ATAI).
Major: AI, Data Science
Contact: Noah Mamié Pascal Severin Andermatt
Master's Project: Designing Multi-Modal and Interactive News Experiences
Modern news consumption is increasingly shaped by short-form, visually engaging, and interactive content. This project examines how these principles — popularized by platforms such as TikTok — can be applied to create a novel, multi-modal, and interactive user experience for news exploration. The goal is to design and prototype an adaptive platform that presents complex articles through short, bite-sized information units combining text, audio, video, and interactive elements.
The project will investigate how multi-modal presentation affects user engagement, comprehension, and trust in news content. It will also explore personalization and user journey modeling — e.g., enabling readers to “dive deeper” into specific aspects of a story or navigate related topics dynamically. Finally, the project aims to integrate and evaluate interactive features that foster active rather than passive news consumption, building on the success of Informfully — a research platform for news recommender systems developed in-house.
If you are interested, please do not hesitate to contact me at the email address provided below. I’d be happy to provide a more detailed project description during a brief meeting. This work contributes to the development of next-generation news interfaces.
Start Date: February 2026
Requirements: Strong software development skills (e.g., React Native), interest in human-AI interaction, and basic familiarity with GenAI models (mostly LLMs).
Recommended: Courses in Software Engineering and Artificial Intelligence.
Major: SoSys, AI. 3-4 students
Contact: Noah Mamié
Master’s Project: Computing Similarities Between Patient and Rare Disease Profiles
Rare diseases are notoriously difficult to diagnose due to heterogeneous symptom presentations and limited case data. A promising approach is to compute similarities between patient symptom profiles and rare disease profiles. These profiles can be structured with the Human Phenotype Ontology (HPO) and linked to diseases in the Orphanet Rare Disease Ontology (ORDO) through the HPO–ORDO Ontological Module (HOOM), forming a rich graph representation of phenotype–disease relationships.
This project aims to implement and compare existing similarity methods, develop a new approach that uses rare disease ontologies, and investigate how multiple similarity measures can be combined into an ensemble to improve retrieval performance. In addition, the project will include a visualization component that highlights phenotype relationships within the ontology, offering both interpretability and insights into the underlying methods.
If interested, feel free to contact me via the email address below. I’m happy to provide a more detailed project description in a short meeting. This work contributes to the RareSim project.
Start Date: February 2026
Requirements: Strong Python coding skills, interest in knowledge graphs, and basic understanding of machine learning. Recommended: the course Advanced Topics in Artificial Intelligence (ATAI). Major AI, SoSys. 3-4 students.
Contact: Pascal Severin Andermatt
Master's Project: Extracting Emotions and Narratives in Political Dialogue
For a deliberative democracy to flourish, it is important that individuals engage in dialogue and express their views and opinions. Current efforts to counter polarisation often focus on exchanging facts or opposing arguments. Yet, previous work has shown that personal narratives empower individuals, particularly those politically disinclined, to engage in political discussions.
This project aims to identify and elicit the emotions and personal narratives underlying political stances. It involves tackling NLP tasks such as emotion recognition, sentiment classification, and narrative extraction, both from short texts and multi-turn dialogues. Additionally, at a conversation level, the project involves developing dialogue management policies to encourage individuals to share non-factual or personal arguments behind their opinions. Students will evaluate and benchmark pre-trained LLMs on these tasks and may extend the work through fine-tuning or adaptive prompting.
The broader aim of this project is to inform the development of politically nuanced chatbots that help users explore their own reasoning and engage constructively across ideological divides.
Start Date: from mid-February 2026
Requirements: Strong Python coding skills and familiarity with ML models (particularly LLMs).
Recommended: Courses in Artificial Intelligence, Natural Language Processing. Interest in Political Science.
Major: AI. 3-4 students
Contact: Selene Báez Santamaría
Master project: Adaptive Questionnaires Platform Development
Voting Advice Applications (VAA) such as Smartvote or Wahl-O-Mat depend on long questionnaires to recommend parties or candidates to a user. Recently, adaptive questionnaires have been introduced to optimize the data collection process and speed up recommendations in such applications. These adaptive questionnaires select the subsequent question based on the individual response profile of a user and, therefore, avoid redundancies.
To demonstrate and test the concept of adaptive questionnaires, the self-hosted AQVAA Platform was built based on Smartvote. Currently, the platform hosts user experiments in a controlled setting. The goal of this Master project is to extend the platform from a research prototype to a live site. This involves understanding and refactoring the code base, implementing additional features, and writing scripts to monitor the performance.
If interested, please contact us at the email address below. We can provide a more detailed description during a meeting.
Note: The Master project is open now. However, the starting date of the project is flexible (ideally before September 2025).
Requirements: Proficiency in Python for backend algorithm development, knowledge of PostgreSQL and Redis for database management and caching, and expertise in Angular, NestJS, and Nginx for front-end integration and deployment.
Contact: Fynn Bachmann